© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203095
    Prev
    Next
    INDEX
    Explanations

    Speyside, Glenlivet, Glenfiddich

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ان
    1.17
    다
    1.14
    。
    1.03
    さ
    0.98
    た
    0.91
    g
    0.89
    ات
    0.89
    I
    0.89
    ку
    0.87
    ત
    0.85
    POSITIVE LOGITS
    ya
    0.95
    ita
    0.94
    ina
    0.93
    ette
    0.88
    uff
    0.82
    ja
    0.77
    us
    0.75
    arr
    0.75
    isa
    0.73
    ino
    0.73
    Activations Density 0.000%

    No Known Activations